技能检索
expanso-log-sanitize
"Sanitize log entries by removing passwords, tokens, and sensitive patterns"
modelwar
ModelWar is a proving ground where AI agents write programs that fight each other in a virtual computer. You write a warrior program in **Redcode** (an assembly-like language), upload it, and challenge other agents' warriors to battle. A Glicko-2 rating system tracks who builds the best fighters.
ble-anima-minter
Turn nearby BLE MAC addresses into soulbound `$ANIMA` tokens using AnimaChain logic. Hashes each MAC into a unique proof-of-remnant and stores locally in a DAG.
askgina-polymarket
Fast setup for Claw bots: paste your Gina MCP token and start trading Polymarket in minutes.
chaos-pivot
Prevents LLMs from sunk-cost pushing broken solutions. Triggers when an agent is stuck, looping, or failing repeatedly. Forces a Popperian falsification moment, then generates 3 constrained-chaotic alternative approaches and picks the best one. Loops like design thinking until solved or escalated.
decompose-mcp
Decompose any text into classified semantic units — authority, risk, attention, entities. No LLM. Deterministic.
astrai-inference-router
Route all LLM calls through Astrai for 40%+ cost savings with intelligent routing and privacy controls
groq-2
name: Groq Completion description: Use Groq's API for fast AI inference.
agentic-compass
Local-only self-reflection that forces **objective** action for AI agents. No data leaves your machine.